Blockchain technology is found to have its applicability in almost every domain because of its advantages such as crypto-security, transparency, immutability, decentralized data network In present times, a smart healthcare system with a blockchain data network and healthcare 40 processes provides transparency, easy and faster accessibility, security, efficiency, etc Healthcare 40 trends include industry 40 processes such as the internet of things (IoT), industrial IoT (IIoT), cognitive computing, artificial intelligence, cloud computing, fog computing, edge computing, etc The goal of this work is to design a smart healthcare system and it is found to be possible through integration and interoperability of Blockchain 30 and Healthcare 40 in consideration with healthcare ground-realities Here, healthcare 40 processes used for data accessibility are targeted to be validated through statistical simulation-optimization methods and algorithms The blockchain is implemented in the Ethereum network, and with associated programming languages, tools, and techniques such as solidity, web3js, Athena, etc Further, this work prepares a comparative and comprehensive survey of state-of-the-art blockchain-based smart healthcare systems The comprehensive survey includes methodology, applications, requirements, outcomes, future directions, etc A list of groups, organizations, and enterprises are prepared that are working in electronic health records (EHR), electronic medical records (EMR) or electronic personal records (EPR) mainly, and a comparative analysis is drawn concerning adopting the blockchain technology in their processes This work has explored optimization algorithms applicable to Healthcare 40 trends and improves the performance of blockchain-based decentralized applications for the smart healthcare system Further, smart contracts and their designs are prepared for the proposed system to expedite the trust-building and payment systems This work has considered simulation and implementation to validate the proposed approach Simulation results show that the Gas value required (indicating block size and expenditure) lies within current Etherum network Gas limits The proposed system is active because block utilization lies above 80% Automated smart contract execution is below 20 seconds A good number (average 3 per simulation time) is generated in the network that indicates a health competition Although there is error observed in simulation and implementation that lies between 055% and 424%, these errors are not affecting overall system performance because simulated and actual (taken in state-of-the-art) data variations are negligible

/pdf/a-novel-smart-healthcare-design-simulation-and-2f4ln6opv8.pdf

A Novel Smart Healthcare Design, Simulation, and Implementation Using Healthcare 4.0 Processes

Nowadays, hand gestures have become a booming area for researchers to work on. In communication, hand gestures play an important role so that humans can communicate through this. So, for accurate communication, it is necessary to capture the real meaning behind any hand gesture so that an appropriate response can be sent back. The correct prediction of gestures is a priority for meaningful communication, which will also enhance human–computer interactions. So, there are several techniques, classifiers, and methods available to improve this gesture recognition. In this research, analysis was conducted on some of the most popular classification techniques such as Naïve Bayes, K-Nearest Neighbor (KNN), random forest, XGBoost, Support vector classifier (SVC), logistic regression, Stochastic Gradient Descent Classifier (SGDC), and Convolution Neural Networks (CNN). By performing an analysis and comparative study on classifiers for gesture recognition, we found that the sign language MNIST dataset and random forest outperform traditional machine-learning classifiers, such as SVC, SGDC, KNN, Naïve Bayes, XG Boost, and logistic regression, predicting more accurate results. Still, the best results were obtained by the CNN algorithm. 

/pdf/an-experimental-analysis-of-various-machine-learning-1ldp74hi.pdf

An Experimental Analysis of Various Machine Learning Algorithms for Hand Gesture Recognition

COVID-19 disease pandemic is affecting the lives of millions of people in one or another manner. To handle the COVID-19 pandemic situation, technological aspects play a vital role in parallel to medical and healthcare facilities. With the use of existing infrastructure, technologies such as artificial intelligence, neural network, blockchain technology, cloud computing, drone-based monitoring, etc. have given the important observations and awareness to many. It is observed that with the combined efforts of technology and healthcare system, recognition of the outbreak is much faster compared to earlier infections. However, many are working continuously to collect and analyze the available COVID-19-related data and introspect the future. The whole of this work is performed to maximize the use of technology and reduce the risk of a continuous outbreak. This work has discussed the recent work done over the use of technologies in handling the COVID-19 scenario. Here, a comparative analysis of various parameters in each technological aspect is discussed to have an understanding of the preferred approaches in different places. Further, brief surveys are conducted in each technological aspect for a better understanding of technological advantage in handling pandemic.

Digital Transformation and Emerging Technologies for COVID-19 Pandemic: Social, Global, and Industry Perspectives

In recent times, the COVID-19 pandemic has affected billions of people worldwide and has resulted in the slowing down of the economy, industry shutdown, job losses, etc. Every country has taken appropriate measures to fight against pandemic by keeping in mind that health is the primary concern for human beings. This work introduces the COVID-19 pandemic and discusses its types, influence over mankind, prevention methods, and latest observations. Further, this study has designed drone-based case studies for pandemic monitoring, social distance measurements, the necessity of the control room, etc. The simulation is designed to have a single-layer drone movement strategy with a fixed distance. The simulation experimentation is derived from real-time drone movement and area coverage for sanitization. The drone movement and collision avoidance strategy are pre-emptive in nature, i.e., drones are derived to move to a fixed location and execute its functionality. At the ground level, service is designed for which people make queues and maintain social distance before being served. This case study shows its successful execution and can be mapped to a real-time environment. Further, a case study is extended to observe the real-time ambulance monitoring for patient pickup and drop at the hospital. Results show its successful working and continuous operation.

Drone-Based Social Distancing, Sanitization, Inspection, Monitoring, and Control Room for COVID-19

Heart diseases are the leading cause of deaths nowadays. Due to the high severity of the problem, it has attracted several researchers around the globe. Researchers have considered the heart diagnosis as a classification problem where meaningful patterns are detected using data mining techniques. This paper presents an evaluation of various supervised learning algorithms and feature selection techniques for heart disease prediction. The performance of six machine learning classifiers (Naive Bayes, Decision Tree, Logistic Regression, Random Forest, Support Vector Machine, k-Nearest Neighbour) and five feature selection techniques (Chi-Square, Gain Ratio, Information Gain, One-R and RELIEF) have been investigated on the benchmark dataset obtained from UCI Machine Learning Repository, Cleveland. The experimental results show that machine learning classifiers can achieve prediction accuracy up to 82.81% for heart disease prediction. The feature selection techniques further improve the classification performance and achieve prediction accuracy up to 83.41%.

Heart Disease Diagnosis: Performance Evaluation of Supervised Machine Learning and Feature Selection Techniques

Identification and quantification of insulin resistance require specific blood test which is complex, time-consuming, and much more invasive, making it difficult to track the changes daily. With the advancement in machine learning approaches, identification of insulin resistance can be carried out without clinical processes. In this work, insulin resistance is identified for individuals with triglycerides and HDL-c ratio using non-invasive techniques employing machine learning approaches. Eighteen parameters are used for identification purposes like age, sex, waist size, height, etc., and combinations of these parameters. Experiments are conducted over the CALERIE dataset. Each output of the attribute selection system is modeled over distinct calculations like logistic regression, CARTs, SVM, LDA, KNN, extra trees classifier. The proposed work is validated with a stratified cross-validation test. Results show that KNN and CatBoost show the best results with an accuracy of 74% and 73% respectively and 1% variance compared to 66% with Bernardini et al. and Stawiski et al. and 83% with Farran et al. With the proposed approach an individual can predict the insulin resistance and hence prospective chances of diabetes might be tracked daily using non-clinical approaches. While the same is not practically possible with clinical processes daily.

A Non-invasive Approach to Identify Insulin Resistance with Triglycerides and HDL-c Ratio Using Machine learning

Radio Frequency IDentification (RFID) is one of the prominent wireless technologies for implementing a complete smart environment and is preferred over magnetic tapes, bar codes and smart cards due...

A Novel and Efficient Reader-to-Reader and Tag-to-Tag Anti-Collision Protocol

Radio Frequency IDentification (RFID) and Wireless Sensor Networks (WSN) are the two most prominent wireless technologies for implementing a complete smart environment for the Internet of Things (IoT). Both RFID and WSN are resource constraint devices, which forces us to go for lightweight cryptography for
security purposes. Security in terms of confidentiality, integrity, authentication, authorization, and availability. Key management is one of the major constraints for resource constraint mobile sensor devices.
This work is an extension of the work done by Kumar et al. using efficient error prediction and limit of agreement for anomaly score. This work ensures cryptographic property, availability, in RFID-WSN integrated network through outlier detection mechanism for 50 to 5000 nodes network. Through detection
ratios and anomaly scores system is tested against outliers. The proposed outlier detection mechanism identifies the inliers and outliers through anomaly score for protection against Denial-of-Service (DoS)
attack. Intruders can be detected in few milliseconds without giving any conflict to the access rights. In terms of throughput, a minimum improvement of 6.2% and a maximum of 219.9% is observed for the proposed
protocol as compared to Kumar et al. Protocol and in terms of percentage of Packet Delivery Ratio (PDR), a minimum improvement of 8.9% and a maximum of 19.5% is observed for the proposed protocol as compared to Kumar et al. protocol.

/pdf/availability-aspects-through-optimization-techniques-based-4vf79p6e0i.pdf

Availability Aspects Through Optimization Techniques Based Outlier Detection Mechanism in Wireless and Mobile Networks

For sharing resources using ad hoc communication MANET are quite effective and scalable medium. MANET is a distributed, decentralized, dynamic network with no fixed infrastructure, which are self- organized and self-managed. Achieving high security level is a major challenge in case of MANET. Layered architecture is one of the ways for handling security challenges, which enables collection and analysis of data from different security dimensions. This work proposes a novel multi-layered outlier detection algorithm using hierarchical similarity metric with hierarchical categorized data. Network performance with and without the presence of outlier is evaluated for different quality-of-service parameters like percentage of APDR and AT for small (100 to 200 nodes), medium (200 to 1000 nodes) and large (1000 to 3000 nodes) scale networks. For a network with and without outliers minimum improvements observed are 9.1 % and 0.61 % for APDR and AT respectively while the maximum improvements of 22.1 % and 104.1 %.

A Multi-layered Outlier Detection Model for Resource Constraint Hierarchical MANET

Authentication is among the initial steps of network formulation. Lightweight authentication processes are preferred for resource-constrained devices. These processes are efficient in terms of computational and communicational costs but inappropriate in providing required security rating. This work explores the feasibility of elliptic curve-based cryptography (ECC) for authentication processes. Three lightweight authentication protocols, which use ECC are identified and analysed for hierarchical network. These protocols are simulated and validated using lightweight cryptography primitives and protocols. In results, it is observed that out of three protocols protocol 1 performs better for 75 and 1000 nodes networks. In comparative analysis, a minimum of 14.1% and maximum of 24.7% throughput improvement is observed. Further, delay is reduced by 15.6% (minimum) and 31.3% (maximum) for protocol 1 as compared to protocol 2 and protocol 3.

Alok Aggarwal

Papers

A Non-invasive Approach to Identify Insulin Resistance with Triglycerides and HDL-c Ratio Using Machine learning

A Novel and Efficient Reader-to-Reader and Tag-to-Tag Anti-Collision Protocol

Availability Aspects Through Optimization Techniques Based Outlier Detection Mechanism in Wireless and Mobile Networks

A Multi-layered Outlier Detection Model for Resource Constraint Hierarchical MANET

Design and Analysis of Elliptic Curve Cryptography-Based Multi-round Authentication Protocols for Resource-Constrained Devices